Skip to main content
Glama

search-pipelines

Search and filter nf-core bioinformatics pipelines using specific queries and pipeline names to streamline workflow selection and management.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pipelineNo
queryYes

Implementation Reference

  • The main handler function for the 'search-pipelines' tool. It recursively searches files in the specified pipeline directory (or root) for the query string, targeting .nf, .config, and .json files, and returns a JSON list of matching file paths.
    async ({ query, pipeline }) => { try { const searchPath = pipeline ? path.join(process.cwd(), pipeline) : process.cwd(); const results: string[] = []; async function searchDir(dir: string) { const entries = await fs.readdir(dir, { withFileTypes: true }); for (const entry of entries) { const fullPath = path.join(dir, entry.name); if (entry.isDirectory() && !entry.name.startsWith('.')) { await searchDir(fullPath); } else if (entry.isFile() && (entry.name.endsWith('.nf') || entry.name.endsWith('.config') || entry.name.endsWith('.json'))) { try { const content = await fs.readFile(fullPath, 'utf-8'); if (content.includes(query)) { results.push(fullPath); } } catch (err) { console.error(`Error reading ${fullPath}: ${err}`); } } } } await searchDir(searchPath); return { content: [{ type: "text", text: JSON.stringify(results, null, 2) }] }; } catch (error) { return { content: [{ type: "text", text: `Error searching pipelines: ${error}` }], isError: true }; } }
  • Zod schema for the tool inputs: 'query' (required string to search for) and 'pipeline' (optional string specifying the pipeline directory).
    { query: z.string(), pipeline: z.string().optional() },
  • src/index.ts:94-145 (registration)
    Registration of the 'search-pipelines' tool on the MCP server using server.tool(name, schema, handler).
    server.tool( "search-pipelines", { query: z.string(), pipeline: z.string().optional() }, async ({ query, pipeline }) => { try { const searchPath = pipeline ? path.join(process.cwd(), pipeline) : process.cwd(); const results: string[] = []; async function searchDir(dir: string) { const entries = await fs.readdir(dir, { withFileTypes: true }); for (const entry of entries) { const fullPath = path.join(dir, entry.name); if (entry.isDirectory() && !entry.name.startsWith('.')) { await searchDir(fullPath); } else if (entry.isFile() && (entry.name.endsWith('.nf') || entry.name.endsWith('.config') || entry.name.endsWith('.json'))) { try { const content = await fs.readFile(fullPath, 'utf-8'); if (content.includes(query)) { results.push(fullPath); } } catch (err) { console.error(`Error reading ${fullPath}: ${err}`); } } } } await searchDir(searchPath); return { content: [{ type: "text", text: JSON.stringify(results, null, 2) }] }; } catch (error) { return { content: [{ type: "text", text: `Error searching pipelines: ${error}` }], isError: true }; } } );

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wjlim/nf-core_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server